Skip to content

Details

Large language models can do more than answer questions, they can take actions. This talk walks through building a chatbot for an internal business app using Java 25 and Spring AI, where the LLM queries databases, performs write operations, and enforces role-based permissions.

We'll cover an agentic loop that gives the application control over each LLM round-trip, "defense in depth" database access, a propose/confirm pattern for write operations, and more (role-based tool visibility, a cheap relevancy gate for off-topic screening, and a sub-agent pattern for context-aware UI navigation help).

About the Speaker
Sujan Kapadia
Sujan Kapadia is the Chief AI Officer at Chariot Solutions, where he leads the company’s AI strategy and execution. Sujan is a practitioner and leader with over 25 years of experience shipping complex systems. He focuses on the practical applications of AI and agents, believing real AI transformation is earned through visible wins, not promises on a roadmap. Companies already have the signal they need, but it gets lost in the noise. Helping them find and use it is the part Sujan loves most.

About the Sponsor
Certara (https://www.certara.com)
Certara accelerates medicines to patients, using biosimulation (modeling and simulation) and technology-enabled services to transform drug discovery and development. Our integrated and proprietary end-to-end platform with generative AI technology, biosimulation, regulatory science, and market access solutions combined with our global 1,400+ strong team of scientists and experts enable informed decision-making, higher R&D productivity, and improved patient outcomes.

Related topics

Events in Radnor, PA
Artificial Intelligence
Java
Software Development
Spring Framework

You may also like